Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 58718
    Prev
    Next
    INDEX
    Explanations

    levels or categories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Calend
    -0.08
     qan
    -0.08
    Our
    -0.08
    Directions
    -0.07
    Invest
    -0.07
    יוון
    -0.07
    Since
    -0.07
    Live
    -0.07
     مدرس
    -0.07
     حاضر
    -0.07
    POSITIVE LOGITS
    等级
    0.21
     tiers
    0.18
    级
    0.18
    級
    0.17
     tier
    0.16
     Levels
    0.16
     स्तर
    0.15
     níveis
    0.15
     levels
    0.14
    阶
    0.14
    Activations Density 0.061%

    No Known Activations